Clean scraped results from the National Archives of South Africa

clean.js

// scraper for http://www.national.archsrch.gov.za/sm300cv/smws/sm300dl
// 
// usage: select results in search results, enter multiple documents view, then copy contents of the results frame to a text file called archives.txt

const fieldnames = ["Document","DEPOT","SOURCE","TYPE","VOLUME_NO","SYSTEM","REFERENCE","PART","DESCRIPTION","STARTING","ENDING","REMARKS.*"]
const replacements = ["",",",",",",",",",",",",",",",",",",",",",""]

var fs = require('fs');
var path = process.cwd();
let d = fs.readFileSync(path + "/archives.txt").toString().replace(/\,/g," ");

let records = d.split("\nDocument ")

var re = /\s*\n/g
records = records.map (r => r = r.replace(re,""))

for (var f of fieldnames) {
	var re = new RegExp(f,"g")
	records = records.map (r => r = r.replace(re,replacements[fieldnames.indexOf(f)]))	
}

var re = /\,\s*/g
records = records.map (r => r = r.replace(re,","))

var re = / +/g
records = records.map (r => r = r.replace(re," "))

headings = fieldnames.slice(0, fieldnames.length-1).join(",")+"\n"

d = headings + records.join("\n")

fs.writeFileSync(path + "/out.txt", d)